Apparatus and method for improving voice recognition
AssigneeElectronics and Telecommunications Research Institute
InventorsJu-Yeob Kim, Bon-Tae Koo, Tae-Joong Kim
Life of this patent
Estimating the term…
Abstract
An apparatus and method for improving voice recognition are disclosed herein. The apparatus includes a standard voice transmission unit, a Mel-frequency cepstrum coefficient (MFCC) generation unit, and an MFCC compensation unit. The standard voice transmission unit generates a standard voice. The MFCC generation unit generates voice feature data (MFCC) based on the utterance of the standard voice before voice recognition. The MFCC compensation unit stores a gain value generated based on the standard voice, and compensates for the distortion of the voice feature data based on the utterance of a user using the gain value during the voice recognition.
Claims9
An apparatus for improving voice recognition, comprising:
- a standard voice transmission unit configured to generate a standard voice;
- a Mel-frequency cepstrum coefficient (MFCC) generation unit configured to generate voice feature data based on an utterance of the standard voice before voice recognition;
- and
- an MFCC compensation unit configured to store a gain value generated based on the standard voice and compensate for a distortion of the voice feature data based on an utterance of a user using the gain value during the voice recognition.
A method for improving voice recognition, comprising:
- generating, by a standard voice transmission unit, a standard voice;
- generating, by an MFCC generation unit, voice feature data based on an utterance of the standard voice before voice recognition;
- and
- compensating for, by an MFCC compensation unit, a distortion of voice feature data generated based on an utterance of a user using a gain value generated based on the standard voice during the voice recognition.
Dependencies are inferred from the claim text.